{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LD7SQQ4SZIXOP3NXENVBEH4NEG","short_pith_number":"pith:LD7SQQ4S","canonical_record":{"source":{"id":"2504.21635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1d3092d88cac482ff71c101d8aa9149c8438bf6bd8ff51c9956a8ed74c0ead1","abstract_canon_sha256":"76fcc5b1a8c418783977f4645cbe0ed082c675cc207df18c2faeed4af7be073b"},"schema_version":"1.0"},"canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","source":{"kind":"arxiv","id":"2504.21635","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21635","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21635v2","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21635","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_12","alias_value":"LD7SQQ4SZIXO","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_16","alias_value":"LD7SQQ4SZIXOP3NX","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_8","alias_value":"LD7SQQ4S","created_at":"2026-07-05T11:56:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LD7SQQ4SZIXOP3NXENVBEH4NEG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1d3092d88cac482ff71c101d8aa9149c8438bf6bd8ff51c9956a8ed74c0ead1","abstract_canon_sha256":"76fcc5b1a8c418783977f4645cbe0ed082c675cc207df18c2faeed4af7be073b"},"schema_version":"1.0"},"canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:56.701976Z","signature_b64":"37bqabXImU3jfRykgftF9eegaMyH3o1em6k3nHlRdbHRyI/DrqVQzPvft1VGMZJY8n52+Ed+yor0/+/91w8EBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","last_reissued_at":"2026-07-05T11:56:56.701465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:56.701465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21635","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61hjEzqlG3RJQwzlzXJJQLqaZfdsSRSMc7BsWrWNKg+sc4SkGH3I6SL0xjiA47b9F84HbOnz6S9mvJ0PvCLnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:13:31.056060Z"},"content_sha256":"291dcc9b55e09a3552f958926fdc0c3d01bf10e42abe60f2373139e56b085ed5","schema_version":"1.0","event_id":"sha256:291dcc9b55e09a3552f958926fdc0c3d01bf10e42abe60f2373139e56b085ed5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LD7SQQ4SZIXOP3NXENVBEH4NEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-04-30T13:37:24Z","abstract_excerpt":"Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21635","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.21635/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mwYVclMlKq5zgmhrlTGxqu9IepWIQUXPoV/nh7ampKmCDYf98rqfAyFt4KTYcy6QSZKtD2M5qfacRdya6ajbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:13:31.056859Z"},"content_sha256":"860be354d0ea2622edfeb51f562eb3074612d3d4f0cc1f0476d5a4d7f9aaeb91","schema_version":"1.0","event_id":"sha256:860be354d0ea2622edfeb51f562eb3074612d3d4f0cc1f0476d5a4d7f9aaeb91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/bundle.json","state_url":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T21:13:31Z","links":{"resolver":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG","bundle":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/bundle.json","state":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LD7SQQ4SZIXOP3NXENVBEH4NEG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76fcc5b1a8c418783977f4645cbe0ed082c675cc207df18c2faeed4af7be073b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","title_canon_sha256":"e1d3092d88cac482ff71c101d8aa9149c8438bf6bd8ff51c9956a8ed74c0ead1"},"schema_version":"1.0","source":{"id":"2504.21635","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21635","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21635v2","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21635","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_12","alias_value":"LD7SQQ4SZIXO","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_16","alias_value":"LD7SQQ4SZIXOP3NX","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_8","alias_value":"LD7SQQ4S","created_at":"2026-07-05T11:56:56Z"}],"graph_snapshots":[{"event_id":"sha256:860be354d0ea2622edfeb51f562eb3074612d3d4f0cc1f0476d5a4d7f9aaeb91","target":"graph","created_at":"2026-07-05T11:56:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.21635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to pro","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21635","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:291dcc9b55e09a3552f958926fdc0c3d01bf10e42abe60f2373139e56b085ed5","target":"record","created_at":"2026-07-05T11:56:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76fcc5b1a8c418783977f4645cbe0ed082c675cc207df18c2faeed4af7be073b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","title_canon_sha256":"e1d3092d88cac482ff71c101d8aa9149c8438bf6bd8ff51c9956a8ed74c0ead1"},"schema_version":"1.0","source":{"id":"2504.21635","kind":"arxiv","version":2}},"canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","first_computed_at":"2026-07-05T11:56:56.701465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:56.701465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"37bqabXImU3jfRykgftF9eegaMyH3o1em6k3nHlRdbHRyI/DrqVQzPvft1VGMZJY8n52+Ed+yor0/+/91w8EBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:56.701976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21635","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:291dcc9b55e09a3552f958926fdc0c3d01bf10e42abe60f2373139e56b085ed5","sha256:860be354d0ea2622edfeb51f562eb3074612d3d4f0cc1f0476d5a4d7f9aaeb91"],"state_sha256":"6c229e8437b76bc70738fa7dc8bd24b2aca101f988ef91979bd1fd331241cc15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVWJV+DzCxbiEh469vk0+s0aQ0L42GWUp+M9yNtLkF3sBax+Eg8K/Z0Ho3Lo/qLDXKNHTb+v7Zadcb5WUhQVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:13:31.063519Z","bundle_sha256":"7d143e6cd5966d5f8a894024dcd95498b23932568f43e57be4d5349551304b58"}}